199 skills · sorted by relevance
Structured performance profiling workflow. Identifies bottlenecks, measures against budgets, and generates optimization recommendations with priority rankings.
The English summary is being prepared. Showing the original description.
Use when debugging CUDA with cuda-gdb or Compute Sanitizer, reading GPU core dumps, using device printf, or triaging error codes 700, 701, 702, and 719. Not for performance: use cuda-profiling.
The English summary is being prepared. Showing the original description.
Interactively gather parameters for `python -m cli.inference.text_generate`, generate a concrete text generation simulation command, explain assumptions, ask for execution confirmation, then run the command and summarize performance metrics. Use when the user wants to validate a specific model, hardware profile, batch/query size, prefill or decode scenario, TP/DP/EP/MOE parallel strategy, profiling database, chrome trace, empirical metrics export, or a best row produced by throughput_optimizer.
The English summary is being prepared. Showing the original description.
Go software engineering skill for designing, implementing, debugging, testing, reviewing, and refactoring Go applications, CLIs, APIs, services, concurrency code, modules, and tooling. Use for .go files, go.mod/go.sum, goroutines/channels, interfaces, error handling, performance profiling, race fixes, and idiomatic Go architecture.
The English summary is being prepared. Showing the original description.
Iterative measurement-driven improvement loop. Measure, profile, mutate, re-measure, commit. Works for performance, bundle size, complexity, test coverage — anything quantifiable. Use when the user wants to systematically improve a metric through repeated cycles of profiling and targeted changes.
The English summary is being prepared. Showing the original description.
Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.
The English summary is being prepared. Showing the original description.
Structured performance profiling workflow. Identifies bottlenecks, measures against budgets, and generates optimization recommendations with priority rankings.
The English summary is being prepared. Showing the original description.
Iterative measurement-driven improvement loop. Measure, profile, mutate, re-measure, commit. Works for performance, bundle size, complexity, test coverage — anything quantifiable. Use when the user wants to systematically improve a metric through repeated cycles of profiling and targeted changes.
The English summary is being prepared. Showing the original description.
DiT 计算模块（L3）：把**已定位的 DiT 计算瓶颈**落成特性级选档与实施—— 量化档（W8A16 / W4A16 / W8A8 系列 / W4A4 / MXFP8 / FA 量化）、稀疏（rf_v2 / ada_bsa）、 缓存（DiTCache / AttentionCache / 时间步优化）、编译启用（MindieSDBackend / Pattern 融合 / ACLGraph） 的**开不开、开哪一档、怎么开、怎么复验**；依据是 `docs/zh/features/*`（特性真源）+ framework-integration/references/framework-support-matrix.md（支持状态）。 即使用户只说"这个模型怎么加速""量化/稀疏/Cache 怎么选怎么开""要不要开量化、开哪一档""这个档位开了有没有效果" 而未提 profiling，也应触发。 **入口条件**：瓶颈点已明确（用户带一句实测锚点，或编排层交付标签）时由域入口 `performance-optimization` 按标签分发到本技能；**瓶颈未明（"怎么加速 / 跑通 / 采 profile"）先走 `model-auto-optimization` 定位**，不在本技能内做占比分析。 near-miss：多卡并行形态 / 通信掩盖 / TP·offload 选型 → `dit-parallel-opt`；VAE 解码段与 host 固定开销 → 各自模块（VAE / host）；单算子实现级实测选型（mindie_bench）→ `benchmark-dev`； 需要新增 pattern / 算子才能落地本档 → `pattern-dev` / `operator-dev`；框架侧开关与使能验证 → `framework-integration`；量化器位级契约与精度对齐（编码公式 / 舍入 / scale 粒度）→ `quantization-dev`；精度验收判据 → `accuracy-gate`；数字入库口径 → `perf-gate`。
The English summary is being prepared. Showing the original description.
Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.
The English summary is being prepared. Showing the original description.
Diagnose and fix Kotlin/Native performance bottlenecks with reproducible tests, lowest-level profiling, and minimal expect/actual optimization patches.
The English summary is being prepared. Showing the original description.
Visualize métricas de treinamento, depure modelos com histogramas, compare experimentos, visualize grafos de modelos e perfil de desempenho com TensorBoard - kit de visualização de ML do Google
The English summary is being prepared. Showing the original description.
Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.
The English summary is being prepared. Showing the original description.
Use when designing, implementing, reviewing, debugging, testing, profiling, or porting concurrent, parallel, distributed, high-performance, network dataplane, kernel-bypass, or real-time software, including locks, semaphores, monitors, MPI, CSP rendezvous, DPDK, VPP, eBPF, XDP, AF_XDP, SR-IOV, RSS, RoCEv2/RDMA, RMS/EDF, priority inversion, and environment selection from silicon to edge.
The English summary is being prepared. Showing the original description.
Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.
The English summary is being prepared. Showing the original description.
Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance issues, or unexpected behavior.
The English summary is being prepared. Showing the original description.
Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.
The English summary is being prepared. Showing the original description.
Android/iOS automated testing: device management, app install, performance profiling, log analysis, screenshot comparison, Maestro E2E orchestration.
The English summary is being prepared. Showing the original description.
Liquid Glass material best practices for SwiftUI, UIKit, and AppKit on iOS 26+/macOS 26+ (Tahoe) through iOS 27/macOS 27. Use when implementing, reviewing, or migrating to glass: glassEffect, Glass variants (.regular/.clear/.identity), tint, interactive(), GlassEffectContainer, glassEffectUnion, toolbar glass, ToolbarSpacer, scrollEdgeEffectStyle, sharedBackgroundVisibility, tabBarMinimizeBehavior, backgroundExtensionEffect, NSGlassEffectView, UIGlassEffect, Tahoe window chrome, glass accessibility (Reduce Transparency/Increase Contrast), pre-26 Material fallbacks, UIDesignRequiresCompatibility. Also fires on symptoms: glass renders dark or muddy, glass looks like a flat tinted rectangle, glass button doesn't register taps, tap passes through glass, "'glassEffect' is only available in iOS 26.0 or newer", "ambiguous use of 'opacity'", "'cornerRadius' was deprecated", glass looks different in simulator vs device, screenshots of glass UI don't match. For glass animation, morphing, glassEffectID, transitions, Metal shaders, or performance profiling use the liquid-glass-motion skill instead.
The English summary is being prepared. Showing the original description.
Debug iOS apps and profile performance using LLDB, Memory Graph Debugger, and Instruments. Use when diagnosing crashes, memory leaks, retain cycles, main thread hangs, slow rendering, build failures, or when profiling CPU, memory, energy, and network usage.
The English summary is being prepared. Showing the original description.
Integrate and optimize Core ML models in iOS apps for on-device machine learning inference. Covers model loading (.mlmodelc, .mlpackage), predictions with auto-generated classes and MLFeatureProvider, compute unit configuration (CPU, GPU, Neural Engine), MLTensor, VNCoreMLRequest, MLComputePlan, multi-model pipelines, and deployment strategies. Use when loading Core ML models, making predictions, configuring compute units, or profiling model performance.
The English summary is being prepared. Showing the original description.
Capture and interpret iOS Simulator ETTrace profiles. Use when profiling launch or runtime latency, comparing traces, or finding CPU-heavy stacks.
The English summary is being prepared. Showing the original description.
Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.
The English summary is being prepared. Showing the original description.
Explore and diagnose a PostHog endpoint's execution logs — error messages, failed runs, cache misses, slow runs, or unexpected row counts during endpoint invocations. Use when the user says "my endpoint is failing", "show me the logs for endpoint X", "what error did endpoint Y produce", "why did endpoint Z return no rows", "is this endpoint hitting cache", or "check the last N runs". Focused on a single named endpoint's runtime log entries, not project-wide auditing or query performance profiling.
The English summary is being prepared. Showing the original description.